Out of stock detection: Datasets & Models

Manual out of stock detection means associates walking every aisle on a schedule, which is slow, inconsistent, and often misses gaps between checks, leading to lost sales and frustrated shoppers who can't find items. Automating shelf monitoring with a detection model gives near-real-time visibility into which shelves are empty or running low, so replenishment can be triggered before a sale is lost. For retail tech teams, this turns shelf auditing from a periodic chore into a continuous, measurable signal that plugs into inventory and task-management systems.

Automated out of stock detection reduces missed sales from empty shelves, speeds up restocking response times, and produces objective shelf-compliance data instead of manual spot checks. It works with existing store cameras, associate smartphones, or shelf-scanning hardware, and scales across aisles and store locations without adding headcount. Built on RF-DETR, the detection pipeline is accurate on dense, cluttered shelf scenes and easy to retrain as product assortments change.

1. Upload an image: Drop any photo into the widget above to try out of stock detection for free, right on this page.
2. Preview instant results: The model detects empty shelf, product, price tag, shelf gap, stocked shelf within seconds and returns an annotated image with structured predictions, so you can immediately see how well it works. Adjust the detection classes and re-run until the results fit your scenario.
3. Like what you see?: With a free Roboflow account, you can deploy this workflow with the Serverless Cloud API, customize it in your workspace, or train RF-DETR on your own images for production accuracy.
4. Get started for free: No code or training data required to begin: upload, review the results, and make it part of your stack in a single click.